Attempt at creating violin plots for 30 high burden countries for 2019 and 2020

AIM: To create violin plots that compare the actual notified cases vs the expected cases in each age group in the 30 high burden countries

Loading the libraries and the data for 2019

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ──────────────────────────────────────────── tidyverse 1.3.1 ──
✓ ggplot2 3.3.5     ✓ purrr   0.3.4
✓ tibble  3.1.3     ✓ dplyr   1.0.7
✓ tidyr   1.1.3     ✓ stringr 1.4.0
✓ readr   2.0.1     ✓ forcats 0.5.1
── Conflicts ─────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(dplyr)
library(magrittr)

Attaching package: ‘magrittr’

The following object is masked from ‘package:purrr’:

    set_names

The following object is masked from ‘package:tidyr’:

    extract

setwd("~/Desktop/AFP/Original Data")

Warning: The working directory was changed to /Users/Lasith/Desktop/AFP/Original Data inside a notebook chunk. The working directory will be reset when the chunk is finished running. Use the knitr root.dir option in the setup chunk to change the working directory for notebook chunks.

estimate_2019 <- read_csv("TBburden.csv")

Rows: 7298 Columns: 13
── Column specification ─────────────────────────────────────────────────────────────
Delimiter: ","
chr (9): country, iso2, iso3, iso_numeric, measure, unit, age_group, sex, risk_fa...
dbl (4): year, best, lo, hi

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

cases_2019 <- read_csv("TBnotif.csv")

Rows: 8492 Columns: 177
── Column specification ─────────────────────────────────────────────────────────────
Delimiter: ","
chr   (5): country, iso2, iso3, iso_numeric, g_whoregion
dbl (172): year, new_sp, new_sn, new_su, new_ep, new_oth, ret_rel, ret_taf, ret_t...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

estimate_2019 %<>% filter(risk_factor == "all")
estimate_2019 %<>% filter(sex != "a")
estimate_2019 <- estimate_2019[, c(1,3,8,9,11,12,13)]

high_estimate <- estimate_2019[estimate_2019$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "India", "Indonesia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

est19_04 <- filter(high_estimate, age_group == "0-4")
est19_514 <- filter(high_estimate, age_group == "5-14")
est19_014 <- filter(high_estimate, age_group == "0-14")
est19_15plus <- filter(high_estimate, age_group == "15plus")

piv19_04 <- pivot_wider(est19_04, names_from = "sex", values_from = c("best", "lo", "hi"))
piv19_04 <- piv19_04[, c(1,2, 5, 7, 9, 4, 6, 8)]

piv19_514 <- pivot_wider(est19_514, names_from = "sex", values_from = c("best", "lo", "hi"))
piv19_514 <- piv19_514[, c(1,2, 5, 7, 9, 4, 6, 8)]

piv19_014 <- pivot_wider(est19_014, names_from = "sex", values_from = c("best", "lo", "hi"))
piv19_014 <- piv19_014[, c(1,2, 5, 7, 9, 4, 6, 8)]

piv19_15plus <- pivot_wider(est19_15plus, names_from = "sex", values_from = c("best", "lo", "hi"))
piv19_15plus <- piv19_15plus[, c(1,2, 5, 7, 9, 4, 6, 8)]

Sorting the notificaiton data for 2019

cases_2019 %<>% filter(year == 2019)
casefilter_2019 <- cases_2019[, c(1,3,5, 100, 103, 104, 113, 115, 118, 119, 128)]

high_case2019 <- casefilter_2019[casefilter_2019$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "India", "Indonesia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

Combining each data frame

violin19_04 <- cbind(piv19_04, high_case2019$newrel_m04, high_case2019$newrel_f04)
colnames(violin19_04)[colnames(violin19_04) == "high_case2019$newrel_m04"] <- "notif_m04"
colnames(violin19_04)[colnames(violin19_04) == "high_case2019$newrel_f04"] <- "notif_f04"

violin19_514 <- cbind(piv19_514, high_case2019$newrel_m514, high_case2019$newrel_f514)
colnames(violin19_514)[colnames(violin19_514) == "high_case2019$newrel_m514"] <- "notif_m514"
colnames(violin19_514)[colnames(violin19_514) == "high_case2019$newrel_f514"] <- "notif_f514"

violin19_014 <- cbind(piv19_014, high_case2019$newrel_m014, high_case2019$newrel_f014)
colnames(violin19_014)[colnames(violin19_014) == "high_case2019$newrel_m014"] <- "notif_m014"
colnames(violin19_014)[colnames(violin19_014) == "high_case2019$newrel_f014"] <- "notif_f014"


violin19_15plus <- cbind(piv19_15plus, high_case2019$newrel_m15plus, high_case2019$newrel_f15plus)
colnames(violin19_15plus)[colnames(violin19_15plus) == "high_case2019$newrel_m15plus"] <- "notif_m15plus"
colnames(violin19_15plus)[colnames(violin19_15plus) == "high_case2019$newrel_f15plus"] <- "notif_f15plus"

Creating boxplots

sub_m04 <- violin19_04[, c(1, 3, 4, 5)]
subpiv_m04 <- pivot_longer(sub_m04, cols = c("best_m", "lo_m", "hi_m"), names_to = "est_m04")
subpiv_m04 <- subpiv_m04[, c(1,3)]
subnot_m04 <- violin19_04[, c(1,9)]
list_m04 <- as.vector(violin19_04$notif_m04)

box_m04 <- boxplot(value ~ country, subpiv_m04, ylab = NULL, horizontal = TRUE, las = 1, cex.names = 0.3, par(mar = c(1, 11, 2, 2)))
points(x = list_m04,
       y = 1:30,
       col = "red",
       pch = 16,)

Creating boxplots and excluding Indonesia and India for 0-4 years

iisub_m04 <- violin19_04[, c(1, 3, 4, 5)]
iisub_m04 %<>% filter(country != c("India", "Indonesia"))
iisubpiv_m04 <- pivot_longer(iisub_m04, cols = c("best_m", "lo_m", "hi_m"), names_to = "est_m04")
iisubpiv_m04 <- iisubpiv_m04[, c(1,3)]
iisubnot_m04 <- violin19_04[, c(1,9)]
iisubnot_m04 %<>% filter(country != c("India", "Indonesia"))

box_m04 <- boxplot(value ~ country, iisubpiv_m04, horizontal = TRUE, las = 1, cex.names = 0.1)
points(x = iisubnot_m04$notif_m04,
       y = 1:28,
       col = "red",
       pch = 16)

iisub_f04 <- violin19_04[, c(1, 6:8)]
iisub_f04 %<>% filter(country != c("India", "Indonesia"))
iisubpiv_f04 <- pivot_longer(iisub_f04, cols = c("best_f", "lo_f", "hi_f"), names_to = "est_f04")
iisubpiv_f04 <- iisubpiv_f04[, c(1,3)]
iisubnot_f04 <- violin19_04[, c(1,10)]
iisubnot_f04 %<>% filter(country != c("India", "Indonesia"))

box_f04 <- boxplot(value ~ country, iisubpiv_f04, horizontal = TRUE, las = 1, cex.names = 0.1)
points(x = iisubnot_f04$notif_f04,
       y = 1:28,
       col = "red",
       pch = 16)

NA
NA

Creating box plots excluding India and Indonesia for 0-14 years

iisub_m014 <- violin19_014[, c(1, 3, 4, 5)]
iisub_m014 %<>% filter(country != c("India", "Indonesia"))
iisubpiv_m014 <- pivot_longer(iisub_m014, cols = c("best_m", "lo_m", "hi_m"), names_to = "est_m014")
iisubpiv_m014 <- iisubpiv_m014[, c(1,3)]
iisubnot_m014 <- violin19_014[, c(1,9)]
iisubnot_m014 %<>% filter(country != c("India", "Indonesia"))

box_m014 <- boxplot(value ~ country, iisubpiv_m014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = iisubnot_m014$notif_m014,
       y = 1:28,
       col = "red",
       pch = 16)

iisub_f014 <- violin19_014[, c(1, 6:8)]
iisub_f014 %<>% filter(country != c("India", "Indonesia"))
iisubpiv_f014 <- pivot_longer(iisub_f014, cols = c("best_f", "lo_f", "hi_f"), names_to = "est_f014")
iisubpiv_f014 <- iisubpiv_f014[, c(1,3)]
iisubnot_f014 <- violin19_014[, c(1,10)]
iisubnot_f014 %<>% filter(country != c("India", "Indonesia"))

box_f014 <- boxplot(value ~ country, iisubpiv_f014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = iisubnot_f014$notif_f014,
       y = 1:28,
       col = "red",
       pch = 16)

Creating box plots for 15plus years

iisub_m15plus <- violin19_15plus[, c(1, 3, 4, 5)]
iisub_m15plus %<>% filter(country != c("India", "Indonesia"))
iisubpiv_m15plus <- pivot_longer(iisub_m15plus, cols = c("best_m", "lo_m", "hi_m"), names_to = "est_m15plus")
iisubpiv_m15plus <- iisubpiv_m15plus[, c(1,3)]
iisubnot_m15plus <- violin19_15plus[, c(1,9)]
iisubnot_m15plus %<>% filter(country != c("India", "Indonesia"))

box_m15plus <- boxplot(value ~ country, iisubpiv_m15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = iisubnot_m15plus$notif_m15plus,
       y = 1:28,
       col = "red",
       pch = 16)

iisub_f15plus <- violin19_15plus[, c(1, 6:8)]
iisub_f15plus %<>% filter(country != c("India", "Indonesia"))
iisubpiv_f15plus <- pivot_longer(iisub_f15plus, cols = c("best_f", "lo_f", "hi_f"), names_to = "est_f04")
iisubpiv_f15plus <- iisubpiv_f15plus[, c(1,3)]
iisubnot_f15plus <- violin19_15plus[, c(1,10)]
iisubnot_f15plus %<>% filter(country != c("India", "Indonesia"))

box_f15plus <- boxplot(value ~ country, iisubpiv_f15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = iisubnot_f15plus$notif_f15plus,
       y = 1:28,
       col = "red",
       pch = 16)

Repeating same data analysis for 2020

setwd("~/Desktop/AFP/modV3/data")
burden_2020 <- read_csv("TB_burden_2020.csv")

Rows: 7277 Columns: 13
── Column specification ─────────────────────────────────────────────────────────────
Delimiter: ","
chr (9): country, iso2, iso3, iso_numeric, measure, unit, age_group, sex, risk_fa...
dbl (4): year, best, lo, hi

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

notif_2020 <- read_csv("TB_notifications.csv")

Warning: One or more parsing issues, see `problems()` for details

Rows: 8707 Columns: 198
── Column specification ─────────────────────────────────────────────────────────────
Delimiter: ","
chr   (5): country, iso2, iso3, iso_numeric, g_whoregion
dbl (191): year, new_sp, new_sn, new_su, new_ep, new_oth, ret_rel, ret_taf, ret_t...
lgl   (2): hiv_all_tpt_completed, hiv_all_tpt_started

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

burden_clean <- filter(burden_2020, risk_factor == "all")
burden_clean %<>% filter(sex != "a")
burden20_04 <- filter(burden_clean, age_group == "0-4")
burden20_514 <- filter(burden_clean, age_group == "5-14")
burden20_014 <- filter(burden_clean, age_group == "0-14")
burden20_15plus <- filter(burden_clean, age_group == "15plus")

burden20_04 <- burden20_04[, c(1,3,9,11,12,13)]
burden20_514 <- burden20_514[, c(1,3,9,11,12,13)]
burden20_014 <- burden20_014[, c(1,3,9,11,12,13)]
burden20_15plus <- burden20_15plus[, c(1,3,9,11,12,13)]

male20_04 <- filter(burden20_04, sex == "m")
female20_04 <- filter(burden20_04, sex == "f")
male20_514 <- filter(burden20_514, sex == "m")
female20_514 <- filter(burden20_514, sex == "f")
male20_014 <- filter(burden20_014, sex == "m")
female20_014 <- filter(burden20_014, sex == "f")
male20_15plus <- filter(burden20_15plus, sex == "m")
female20_15plus <- filter(burden20_15plus, sex == "f")

#Pivoted tables of estimates for creation of bar plots 
pivmale_04 <- pivot_longer(male20_04, cols = c("best", "lo", "hi"), names_to = "est")
pivmale_04 <- pivmale_04[, c(1,4)]
pivfemale_04 <- pivot_longer(female20_04, cols = c("best", "lo", "hi"), names_to = "est")
pivfemale_04 <- pivfemale_04[, c(1,4)]
pivmale_514 <- pivot_longer(male20_514, cols = c("best", "lo", "hi"), names_to = "est")
pivmale_514 <- pivmale_514[, c(1,4)]
pivfemale_514 <- pivot_longer(female20_514, cols = c("best", "lo", "hi"), names_to = "est")
pivfemale_514 <- pivfemale_514[, c(1,4)]
pivmale_014 <- pivot_longer(male20_014, cols = c("best", "lo", "hi"), names_to = "est")
pivmale_014 <- pivmale_014[, c(1,4)]
pivfemale_014 <- pivot_longer(female20_014, cols = c("best", "lo", "hi"), names_to = "est")
pivfemale_014 <- pivfemale_014[, c(1,4)]
pivmale_15plus <- pivot_longer(male20_15plus, cols = c("best", "lo", "hi"), names_to = "est")
pivmale_15plus <- pivmale_15plus[, c(1,4)]
pivfemale_15plus <- pivot_longer(female20_15plus, cols = c("best", "lo", "hi"), names_to = "est")
pivfemale_15plus <- pivfemale_15plus[, c(1,4)]

#Extracting the notification data for 2020 to add to the bar plot 
notif_2020 %<>% filter(year == 2020)
comboM20_04 <- merge(male20_04, notif_2020[, c(3, 100)], by = "iso3")
comboM20_514 <- merge(male20_514, notif_2020[, c(3, 103)], by = "iso3")
comboM20_014 <- merge(male20_014, notif_2020[, c(3, 104)], by = "iso3")
comboM20_15plus <- merge(male20_15plus, notif_2020[, c(3, 113)], by = "iso3")

comboF20_04 <- merge(female20_04, notif_2020[, c(3, 115)], by = "iso3")
comboF20_514 <- merge(female20_514, notif_2020[, c(3, 118)], by = "iso3")
comboF20_014 <- merge(female20_014, notif_2020[, c(3, 119)], by = "iso3")
comboF20_15plus <- merge(female20_15plus, notif_2020[, c(3, 128)], by = "iso3")

Isolating the data for high burden countries excluding India and Indonesia

ii_2020_m04 <-  comboM20_04[comboM20_04$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_f04 <-  comboF20_04[comboF20_04$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_m514 <-  comboM20_514[comboM20_514$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_f514 <-  comboF20_514[comboF20_514$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_m014 <-  comboM20_014[comboM20_014$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_f014 <-  comboF20_014[comboF20_014$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_m15plus <-  comboM20_15plus[comboM20_15plus$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

ii_2020_f15plus <-  comboF20_15plus[comboF20_15plus$country %in% c("Angola", "Bangladesh", "Brazil", "China", "Democratic People's Republic of Korea", "Democratic Republic of the Congo", "Ethiopia", "Kenya", "Mozambique", "Myanmar", "Nigeria", "Pakistan", "Philippines", "Russian Federation", "South Africa", "Thailand", "United Republic of Tanzania", "Viet Nam", "Cambodia", "Central African Republic", "Congo", "Lesotho", "Liberia", "Namibia", "Papua New Guinea", "Sierra Leone", "Zambia", "Zimbabwe"), ]

Prepping data for box plots

topiv_m04 <- ii_2020_m04[, c(2,4:6)]
pivved_m04 <- pivot_longer(topiv_m04, cols = c("best", "lo", "hi"), names_to = "est")
pivved_m04 <- pivved_m04[, c(1,3)]

topiv_f04 <- ii_2020_f04[, c(2,4:6)]
pivved_f04 <- pivot_longer(topiv_f04, cols = c("best", "lo", "hi"), names_to = "est")
pivved_f04 <- pivved_f04[, c(1,3)]

topiv_m514 <- ii_2020_m514[, c(2,4:6)]
pivved_m514 <- pivot_longer(topiv_m514, cols = c("best", "lo", "hi"), names_to = "est")
pivved_m514 <- pivved_m514[, c(1,3)]

topiv_f514 <- ii_2020_f514[, c(2,4:6)]
pivved_f514 <- pivot_longer(topiv_f514, cols = c("best", "lo", "hi"), names_to = "est")
pivved_f514 <- pivved_f514[, c(1,3)]

topiv_m014 <- ii_2020_m014[, c(2,4:6)]
pivved_m014 <- pivot_longer(topiv_m014, cols = c("best", "lo", "hi"), names_to = "est")
pivved_m014 <- pivved_m014[, c(1,3)]

topiv_f014 <- ii_2020_f014[, c(2,4:6)]
pivved_f014 <- pivot_longer(topiv_f014, cols = c("best", "lo", "hi"), names_to = "est")
pivved_f014 <- pivved_f014[, c(1,3)]


topiv_m15plus <- ii_2020_m15plus[, c(2,4:6)]
pivved_m15plus <- pivot_longer(topiv_m15plus, cols = c("best", "lo", "hi"), names_to = "est")
pivved_m15plus <- pivved_m15plus[, c(1,3)]


topiv_f15plus <- ii_2020_f15plus[, c(2,4:6)]
pivved_f15plus <- pivot_longer(topiv_f15plus, cols = c("best", "lo", "hi"), names_to = "est")
pivved_f15plus <- pivved_f15plus[, c(1,3)]

Creating box plots for high burden countries excluding

box20_m04 <- boxplot(value ~ country, pivved_m04, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_m04 <- ii_2020_m04[order(ii_2020_m04$country), ]
points(x = ii_2020_m04$newrel_m04,
       y = 1:28,
       col = "red",
       pch = 16)

box20_f04 <- boxplot(value ~ country, pivved_f04, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_f04 <- ii_2020_f04[order(ii_2020_f04$country), ]
points(x = ii_2020_f04$newrel_f04,
       y = 1:28,
       col = "red",
       pch = 16)

box20_m514 <- boxplot(value ~ country, pivved_m514, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_m514 <- ii_2020_m514[order(ii_2020_m514$country), ]
points(x = ii_2020_m514$newrel_m514,
       y = 1:28,
       col = "red",
       pch = 16)

box20_f514 <- boxplot(value ~ country, pivved_f514, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_f514 <- ii_2020_f514[order(ii_2020_f514$country), ]
points(x = ii_2020_f514$newrel_f514,
       y = 1:28,
       col = "red",
       pch = 16)

box20_m014 <- boxplot(value ~ country, pivved_m014, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_m014 <- ii_2020_m014[order(ii_2020_m014$country), ]
points(x = ii_2020_m014$newrel_m014,
       y = 1:28,
       col = "red",
       pch = 16)

box20_f014 <- boxplot(value ~ country, pivved_f014, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_f014 <- ii_2020_f014[order(ii_2020_f014$country), ]
points(x = ii_2020_f014$newrel_f014,
       y = 1:28,
       col = "red",
       pch = 16)

box20_m15plus <- boxplot(value ~ country, pivved_m15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_m15plus <- ii_2020_m15plus[order(ii_2020_m15plus$country), ]
points(x = ii_2020_m15plus$newrel_m15plus,
       y = 1:28,
       col = "red",
       pch = 16)

box20_f15plus <- boxplot(value ~ country, pivved_f15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
ii_2020_f15plus <- ii_2020_f15plus[order(ii_2020_f15plus$country), ]
points(x = ii_2020_f15plus$newrel_f15plus,
       y = 1:28,
       col = "red",
       pch = 16)

Performing same analysis by continent starting with 2019 data

est19_04 <- filter(estimate_2019, age_group == "0-4")
est19_514 <- filter(estimate_2019, age_group == "5-14")
est19_014 <- filter(estimate_2019, age_group == "0-14")
est19_15plus <- filter(estimate_2019, age_group == "15plus")

estM19_04 <- filter(est19_04, sex == "m")
estF19_04 <- filter(est19_04, sex == "f")
estM19_514 <- filter(est19_514, sex == "m")
estF19_514 <- filter(est19_514, sex == "f")
estM19_014 <- filter(est19_014, sex == "m")
estF19_014 <- filter(est19_014, sex == "f")
estM19_15plus <- filter(est19_15plus, sex == "m")
estF19_15plus <- filter(est19_15plus, sex == "f")

estM19_04 <- estM19_04[, -c(3,4)]
estF19_04 <- estF19_04[, -c(3,4)]
estM19_514 <- estM19_514[, -c(3,4)]
estF19_514 <- estF19_514[, -c(3,4)]
estM19_014 <- estM19_014[, -c(3,4)]
estF19_014 <- estF19_014[, -c(3,4)]
estM19_15plus <- estM19_15plus[, -c(3,4)]
estF19_15plus <- estF19_15plus[, -c(3,4)]

###Adding in the case notification data for 2019
tot_19_m04 <- merge(estM19_04, casefilter_2019[,c(1:4)], by = c("country", "iso3"))
tot_19_m04 <- tot_19_m04[,c(1,2,6,3:5, 7)]
colnames(tot_19_m04)[colnames(tot_19_m04) == "newrel_m04"] <- "cases"

tot_19_f04 <- merge(estF19_04, casefilter_2019[,c(1:3, 8)], by = c("country", "iso3"))
tot_19_f04 <- tot_19_f04[,c(1,2,6,3:5, 7)]
colnames(tot_19_f04)[colnames(tot_19_f04) == "newrel_f04"] <- "cases"

tot_19_m514 <- merge(estM19_514, casefilter_2019[,c(1:3, 5)], by = c("country", "iso3"))
tot_19_m514 <- tot_19_m514[,c(1,2,6,3:5, 7)]
colnames(tot_19_m514)[colnames(tot_19_m514) == "newrel_m514"] <- "cases"

tot_19_f514 <- merge(estF19_514, casefilter_2019[,c(1:3, 9)], by = c("country", "iso3"))
tot_19_f514 <- tot_19_f514[,c(1,2,6,3:5, 7)]
colnames(tot_19_f514)[colnames(tot_19_f514) == "newrel_f514"] <- "cases"

tot_19_m014 <- merge(estM19_014, casefilter_2019[,c(1:3, 6)], by = c("country", "iso3"))
tot_19_m014 <- tot_19_m014[,c(1,2,6,3:5, 7)]
colnames(tot_19_m014)[colnames(tot_19_m014) == "newrel_m014"] <- "cases"

tot_19_f014 <- merge(estF19_014, casefilter_2019[,c(1:3, 10)], by = c("country", "iso3"))
tot_19_f014 <- tot_19_f014[,c(1,2,6,3:5, 7)]
colnames(tot_19_f014)[colnames(tot_19_f014) == "newrel_f014"] <- "cases"

tot_19_m15plus <- merge(estM19_15plus, casefilter_2019[,c(1:3, 7)], by = c("country", "iso3"))
tot_19_m15plus <- tot_19_m15plus[,c(1,2,6,3:5, 7)]
colnames(tot_19_m15plus)[colnames(tot_19_m15plus) == "newrel_m15plus"] <- "cases"

tot_19_f15plus <- merge(estF19_15plus, casefilter_2019[,c(1:3, 11)], by = c("country", "iso3"))
tot_19_f15plus <- tot_19_f15plus[,c(1,2,6,3:5, 7)]
colnames(tot_19_f15plus)[colnames(tot_19_f15plus) == "newrel_f15plus"] <- "cases"


##Extracting information percontinent 
sum_best_m04 <- tot_19_m04 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_m04 <- tot_19_m04 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_m04 <- tot_19_m04 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_m04 <- tot_19_m04 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_m04 <- cbind(sum_best_m04, sum_lo_m04$total, sum_hi_m04$total, sum_cases_m04$total)
colnames(merge19_m04) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_f04 <- tot_19_f04 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_f04 <- tot_19_f04 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_f04 <- tot_19_f04 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_f04 <- tot_19_f04 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_f04 <- cbind(sum_best_f04, sum_lo_f04$total, sum_hi_f04$total, sum_cases_f04$total)
colnames(merge19_f04) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_m014 <- tot_19_m014 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_m014 <- tot_19_m014 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_m014 <- tot_19_m014 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_m014 <- tot_19_m014 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_m014 <- cbind(sum_best_m014, sum_lo_m014$total, sum_hi_m014$total, sum_cases_m014$total)
colnames(merge19_m014) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_f014 <- tot_19_f014 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_f014 <- tot_19_f014 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_f014 <- tot_19_f014 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_f014 <- tot_19_f014 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_f014 <- cbind(sum_best_f014, sum_lo_f014$total, sum_hi_f014$total, sum_cases_f014$total)
colnames(merge19_f014) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_m514 <- tot_19_m514 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_m514 <- tot_19_m514 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_m514 <- tot_19_m514 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_m514 <- tot_19_m514 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_m514 <- cbind(sum_best_m514, sum_lo_m514$total, sum_hi_m514$total, sum_cases_m514$total)
colnames(merge19_m514) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_f514 <- tot_19_f514 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_f514 <- tot_19_f514 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_f514 <- tot_19_f514 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_f514 <- tot_19_f514 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_f514 <- cbind(sum_best_f514, sum_lo_f514$total, sum_hi_f514$total, sum_cases_f514$total)
colnames(merge19_f514) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_m15plus <- tot_19_m15plus %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_m15plus <- tot_19_m15plus %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_m15plus <- tot_19_m15plus %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_m15plus <- tot_19_m15plus %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_m15plus <- cbind(sum_best_m15plus, sum_lo_m15plus$total, sum_hi_m15plus$total, sum_cases_m15plus$total)
colnames(merge19_m15plus) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum_best_f15plus <- tot_19_f15plus %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum_lo_f15plus <- tot_19_f15plus %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum_hi_f15plus <- tot_19_f15plus %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum_cases_f15plus <- tot_19_f15plus %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge19_f15plus <- cbind(sum_best_f15plus, sum_lo_f15plus$total, sum_hi_f15plus$total, sum_cases_f15plus$total)
colnames(merge19_f15plus) <- c("g_whoregion", "best", "lo", "hi", "cases")

Plotting boxplots for continent data for 2019

pivtot_m04 <- pivot_longer(merge19_m04, cols = c("best", "lo", "hi"), names_to = "est")
box19_m04 <- boxplot(value ~ g_whoregion, pivtot_m04, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_m04$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_f04 <- pivot_longer(merge19_f04, cols = c("best", "lo", "hi"), names_to = "est")
box19_f04 <- boxplot(value ~ g_whoregion, pivtot_f04, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_f04$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_m514 <- pivot_longer(merge19_m514, cols = c("best", "lo", "hi"), names_to = "est")
box19_m514 <- boxplot(value ~ g_whoregion, pivtot_m514, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_m514$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_f514 <- pivot_longer(merge19_f514, cols = c("best", "lo", "hi"), names_to = "est")
box19_f514 <- boxplot(value ~ g_whoregion, pivtot_f514, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_f514$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_m014 <- pivot_longer(merge19_m014, cols = c("best", "lo", "hi"), names_to = "est")
box19_m014 <- boxplot(value ~ g_whoregion, pivtot_m014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_m014$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_f014 <- pivot_longer(merge19_f014, cols = c("best", "lo", "hi"), names_to = "est")
box19_f014 <- boxplot(value ~ g_whoregion, pivtot_f014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_f014$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_m15plus <- pivot_longer(merge19_m15plus, cols = c("best", "lo", "hi"), names_to = "est")
box19_m15plus <- boxplot(value ~ g_whoregion, pivtot_m15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_m15plus$cases,
       y = 1:6,
       col = "red",
       pch = 16)

pivtot_f15plus <- pivot_longer(merge19_f15plus, cols = c("best", "lo", "hi"), names_to = "est")
box19_f15plus <- boxplot(value ~ g_whoregion, pivtot_f15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge19_f15plus$cases,
       y = 1:6,
       col = "red",
       pch = 16)

Performing continental analysis with 2020 data

#Adding g_whoregion to the combined data frames
regionM20_04 <- merge(male20_04, notif_2020[, c(3, 5,100)], by = "iso3")
regionM20_514 <- merge(male20_514, notif_2020[, c(3, 5, 103)], by = "iso3")
regionM20_014 <- merge(male20_014, notif_2020[, c(3, 5, 104)], by = "iso3")
regionM20_15plus <- merge(male20_15plus, notif_2020[, c(3, 5, 113)], by = "iso3")

regionF20_04 <- merge(female20_04, notif_2020[, c(3, 5, 115)], by = "iso3")
regionF20_514 <- merge(female20_514, notif_2020[, c(3, 5, 118)], by = "iso3")
regionF20_014 <- merge(female20_014, notif_2020[, c(3, 5, 119)], by = "iso3")
regionF20_15plus <- merge(female20_15plus, notif_2020[, c(3, 5, 128)], by = "iso3")

colnames(regionM20_04)[colnames(regionM20_04) == "newrel_m04"] <- "cases"
colnames(regionM20_514)[colnames(regionM20_514) == "newrel_m514"] <- "cases"
colnames(regionM20_014)[colnames(regionM20_014) == "newrel_m014"] <- "cases"
colnames(regionM20_15plus)[colnames(regionM20_15plus) == "newrel_m15plus"] <- "cases"

colnames(regionF20_04)[colnames(regionF20_04) == "newrel_f04"] <- "cases"
colnames(regionF20_514)[colnames(regionF20_514) == "newrel_f514"] <- "cases"
colnames(regionF20_014)[colnames(regionF20_014) == "newrel_f014"] <- "cases"
colnames(regionF20_15plus)[colnames(regionF20_15plus) == "newrel_f15plus"] <- "cases"

#Creating data for the boxplots 
sum20_best_m04 <- regionM20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_m04 <- regionM20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_m04 <- regionM20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_m04 <- regionM20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_m04 <- cbind(sum20_best_m04, sum20_lo_m04$total, sum20_hi_m04$total, sum20_cases_m04$total)
colnames(merge20_m04) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_f04 <- regionF20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_f04 <- regionF20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_f04 <- regionF20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_f04 <- regionF20_04 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_f04 <- cbind(sum20_best_f04, sum20_lo_f04$total, sum20_hi_f04$total, sum20_cases_f04$total)
colnames(merge20_f04) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_m514 <- regionM20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_m514 <- regionM20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_m514 <- regionM20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_m514 <- regionM20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_m514 <- cbind(sum20_best_m514, sum20_lo_m514$total, sum20_hi_m514$total, sum20_cases_m514$total)
colnames(merge20_m514) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_f514 <- regionF20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_f514 <- regionF20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_f514 <- regionF20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_f514 <- regionF20_514 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_f514 <- cbind(sum20_best_f514, sum20_lo_f514$total, sum20_hi_f514$total, sum20_cases_f514$total)
colnames(merge20_f514) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_m014 <- regionM20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_m014 <- regionM20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_m014 <- regionM20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_m014 <- regionM20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_m014 <- cbind(sum20_best_m014, sum20_lo_m014$total, sum20_hi_m014$total, sum20_cases_m014$total)
colnames(merge20_m014) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_f014 <- regionF20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_f014 <- regionF20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_f014 <- regionF20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_f014 <- regionF20_014 %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_f014 <- cbind(sum20_best_f014, sum20_lo_f014$total, sum20_hi_f014$total, sum20_cases_f014$total)
colnames(merge20_f014) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_m15plus <- regionM20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_m15plus <- regionM20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_m15plus <- regionM20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_m15plus <- regionM20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_m15plus <- cbind(sum20_best_m15plus, sum20_lo_m15plus$total, sum20_hi_m15plus$total, sum20_cases_m15plus$total)
colnames(merge20_m15plus) <- c("g_whoregion", "best", "lo", "hi", "cases")

sum20_best_f15plus <- regionF20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(best))
sum20_lo_f15plus <- regionF20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(lo))
sum20_hi_f15plus <- regionF20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(hi))
sum20_cases_f15plus <- regionF20_15plus %>% group_by(g_whoregion) %>% summarise(total = sum(na.omit(cases)))
merge20_f15plus <- cbind(sum20_best_f15plus, sum20_lo_f15plus$total, sum20_hi_f15plus$total, sum20_cases_f15plus$total)
colnames(merge20_f15plus) <- c("g_whoregion", "best", "lo", "hi", "cases")


#Drawing box plots for 2020

piv20_m04 <- pivot_longer(merge20_m04, cols = c("best", "lo", "hi"), names_to = "est")
box20_m04 <- boxplot(value ~ g_whoregion, piv20_m04, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_m04$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_f04 <- pivot_longer(merge20_f04, cols = c("best", "lo", "hi"), names_to = "est")
box20_f04 <- boxplot(value ~ g_whoregion, piv20_f04, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_f04$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_m514 <- pivot_longer(merge20_m514, cols = c("best", "lo", "hi"), names_to = "est")
box20_m514 <- boxplot(value ~ g_whoregion, piv20_m514, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_m514$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_f514 <- pivot_longer(merge20_f514, cols = c("best", "lo", "hi"), names_to = "est")
box20_f514 <- boxplot(value ~ g_whoregion, piv20_f514, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_f514$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_m014 <- pivot_longer(merge20_m014, cols = c("best", "lo", "hi"), names_to = "est")
box20_m014 <- boxplot(value ~ g_whoregion, piv20_m014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_m014$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_f014 <- pivot_longer(merge20_f014, cols = c("best", "lo", "hi"), names_to = "est")
box20_f014 <- boxplot(value ~ g_whoregion, piv20_f014, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_f014$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_m15plus <- pivot_longer(merge20_m15plus, cols = c("best", "lo", "hi"), names_to = "est")
box20_m15plus <- boxplot(value ~ g_whoregion, piv20_m15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_m15plus$cases,
       y = 1:6,
       col = "red",
       pch = 16)

piv20_f15plus <- pivot_longer(merge20_f15plus, cols = c("best", "lo", "hi"), names_to = "est")
box20_f15plus <- boxplot(value ~ g_whoregion, piv20_f15plus, horizontal = TRUE, las = 1, cex.names = 0.5)
points(x = merge20_f15plus$cases,
       y = 1:6,
       col = "red",
       pch = 16)

Creating comibned data frame comparing 2019 and 2020 data

#Age 04 side-by-side
sexM <- "male"
merg_m04 <- merge(pivtot_m04, piv20_m04, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_m04) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_m04 <- cbind(merg_m04, sexM)
colnames(merg_m04)[colnames(merg_m04) == "sexM"] <- "sex"

sexF <- "female"
merg_f04 <- merge(pivtot_f04, piv20_f04, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_f04) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_f04 <- cbind(merg_f04, sexF)
colnames(merg_f04)[colnames(merg_f04) == "sexF"] <- "sex"

merged_04 <- rbind(merg_m04, merg_f04)
merged_044 <- merged_04[, -c(3,5)]
long_04 <- pivot_longer(merged_044, cols = c("est_2019", "est_2020"))

gg_try04 <- ggplot(long_04, aes(x = g_whoregion, y = value, color = name)) + geom_boxplot() + facet_wrap(~long_04$sex)

#Age 5-14 side-by-side
sexM <- "male"
merg_m514 <- merge(pivtot_m514, piv20_m514, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_m514) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_m514 <- cbind(merg_m514, sexM)
colnames(merg_m514)[colnames(merg_m514) == "sexM"] <- "sex"

sexF <- "female"
merg_f514 <- merge(pivtot_f514, piv20_f514, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_f514) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_f514 <- cbind(merg_f514, sexF)
colnames(merg_f514)[colnames(merg_f514) == "sexF"] <- "sex"

merged_514 <- rbind(merg_m514, merg_f514)
merged_5144 <- merged_514[, -c(3,5)]
long_514 <- pivot_longer(merged_5144, cols = c("est_2019", "est_2020"))

gg_try514 <- ggplot(long_514, aes(x = g_whoregion, y = value, color = name)) + geom_boxplot() + facet_wrap(~long_514$sex)

#Age 15 plus side-by-side
sexM <- "male"
merg_m15plus <- merge(pivtot_m15plus, piv20_m15plus, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_m15plus) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_m15plus <- cbind(merg_m15plus, sexM)
colnames(merg_m15plus)[colnames(merg_m15plus) == "sexM"] <- "sex"

sexF <- "female"
merg_f15plus <- merge(pivtot_f15plus, piv20_f15plus, by = c("g_whoregion", "est"), all.x = TRUE)
colnames(merg_f15plus) <- c("g_whoregion", "est", "case_2019", "est_2019", "case_2020", "est_2020")
merg_f15plus <- cbind(merg_f15plus, sexF)
colnames(merg_f15plus)[colnames(merg_f15plus) == "sexF"] <- "sex"

merged_15plus <- rbind(merg_m15plus, merg_f15plus)
merged_15plus4 <- merged_15plus[, -c(3,5)]
long_15plus <- pivot_longer(merged_15plus4, cols = c("est_2019", "est_2020"))

gg_try15plus <- ggplot(long_15plus, aes(x = g_whoregion, y = value, color = name)) + geom_boxplot() + facet_wrap(~long_15plus$sex) 

Creating data frame to overlay the case data for each graph

cases_04 <- merged_04[, -c(2, 4,6)]
case_ready04 <- pivot_longer(cases_04, cols = c("case_2019", "case_2020"))

no_dups04 <- case_ready04[!duplicated(case_ready04),]

gg_try04 <- ggplot(long_04, aes(x = g_whoregion, y = value, color = name)) + geom_boxplot() + facet_wrap(~long_04$sex)


gg_alone <- ggplot(no_dups04, aes(x = g_whoregion, y = value, color = name)) + geom_point() + facet_wrap(~no_dups04$sex)

gg_try05 <- ggplot(long_04, aes(x = g_whoregion, y = value, color = name)) + geom_boxplot() + geom_point(data = no_dups04, aes(x = g_whoregion, y = value, color = name), inherit.aes = )  + facet_wrap(~long_04$sex)


###Trying again 
merged_05 <- merged_04[, -2]
incl_case <- pivot_longer(merged_05, cols = c("est_2019", "est_2020"))
incl_case2 <- pivot_longer(incl_case, cols = c("case_2019", "case_2020"), values_to = "cases", names_repair= "unique")

New names:
* name -> name...3
* name -> name...5

colnames(incl_case2) <- c("g_whoregion", "sex", "est", "est_value", "case", "case_value")

gg_incl04 <- ggplot(incl_case2, aes(x = g_whoregion, y = est_value, color = est)) + geom_boxplot() + geom_point(aes(x = g_whoregion, y = case_value, color = case)) + facet_wrap(~incl_case2$sex) + labs(title = "2019 vs 2020 estimate and notification data for 0-4 yrs")

gg_incl04

##Trying5-14 
merged_514_ready <- merged_514[, -2]
incl_case514 <- pivot_longer(merged_514_ready, cols = c("est_2019", "est_2020"))
incl_case5142 <- pivot_longer(incl_case514, cols = c("case_2019", "case_2020"), values_to = "cases", names_repair= "unique")

New names:
* name -> name...3
* name -> name...5

colnames(incl_case5142) <- c("g_whoregion", "sex", "est", "est_value", "case", "case_value")

gg_incl514 <- ggplot(incl_case5142, aes(x = g_whoregion, y = est_value, color = est)) + geom_boxplot() + geom_point(aes(x = g_whoregion, y = case_value, color = case)) + facet_wrap(~incl_case5142$sex) + labs(title = "2019 vs 2020 estimate and notification data for 5-14 yrs")
gg_incl514

#Trying 15plus
merged_15plus_ready <- merged_15plus[, -2]
incl_case15plus <- pivot_longer(merged_15plus_ready, cols = c("est_2019", "est_2020"))
incl_case15plus2 <- pivot_longer(incl_case15plus, cols = c("case_2019", "case_2020"), values_to = "cases", names_repair= "unique")

New names:
* name -> name...3
* name -> name...5

colnames(incl_case15plus2) <- c("g_whoregion", "sex", "est", "est_value", "case", "case_value")

gg_incl15plus <- ggplot(incl_case15plus2, aes(x = g_whoregion, y = est_value, color = est)) + geom_boxplot() + geom_point(aes(x = g_whoregion, y = case_value, color = case)) + facet_wrap(~incl_case15plus2$sex) + labs(title = "2019 vs 2020 estimate and notification data for 15plus yrs")
gg_incl15plus

NA
NA